A consumer purchasing model with learning and departure behaviour
- PDF / 367,143 Bytes
- 9 Pages / 595 x 842 pts (A4) Page_size
- 79 Downloads / 200 Views
#2000 Operational Research Society Ltd. All rights reserved. 0160-5682/00 $15.00 www.stockton-press.co.uk/jors
A consumer purchasing model with learning and departure behaviour C Wu1* and H-L Chen2 1
National Taiwan University of Science and Technology; 2Ming-Chuan University, Taipei, Taiwan
The purpose of this paper is to extend the model of negative binominal distribution used in consumer purchasing models so as to incorporate the consumer's learning and departure behaviours. The regularity of interpurchase time and its unobserved heterogeneity are also included. Due to these extensions, this model can be used to determine during a given period how many purchases are made by an experienced or an inexperienced customer. This model also allows the determination of the probability that a customer with a given pattern of purchasing behaviour still remains, or has departed, at any time after k 5 1 purchases are made. An illustration of the approach is conducted using consumer purchase data for tea. As assessed by comparing results with Theil's U, the integrated model developed gives the best results and shows that learning and departure are important factors which in¯uence consumer's purchase behaviour, especially, when evaluating the behaviour of inexperienced customers. Keywords: customer purchasing; interpurchase time; learning; purchase behaviour
Introduction The manner in which a customer makes purchases has long been of interest to marketing researchers and practitioners. The negative binomial distribution (NBD) model gives a good starting point for research into consumer purchasing behaviour. The so-called NBD-type models, by assuming a Poisson purchase process and exponential interpurchase time, and by adding gamma heterogeneity across a population, give an approximate ®t for frequently purchased products.1 Many researchers have further attempted to improve the NBD model by adding marketing variables1±6 or by considering the covariance between these variables and purchase rates.7,8 Gupta9 summarises this work by noting that the alternative approaches of NBD-type models capture the effect of marketing variables on customers' purchase time decisions, but do not directly extend traditionally used stochastic models. However, only adding marketing variables and not extending the model to ®t real consumers' purchasing behaviour is not nearly as useful as ®rst extending the model to encompass real customer purchasing behaviour, then incorporating the effects of marketing variables. This is true not only for predictive purposes but also for diagnostic purposes. Most of the NBD-type models are applied in steady state, that is they assume all the consumers are sophisticated. However, such an assumption can be too restricted, since *Correspondence: Dr C Wu, Department of Business Administration, National Taiwan University of Science and Technology, 43 Sec. 4, Keelung Road, Taipei, Taiwan, R.O.C. E-mail: [email protected]
the majority of a ®rm's customers may be inexperienced or may even be new customers. Therefore,
Data Loading...
